Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted

Pull networking updates from Jakub Kicinski:
 "Core:

   - Add dedicated kmem_cache for typical/small skb->head, avoid having
     to access struct page at kfree time, and improve memory use.

   - Introduce sysctl to set default RPS configuration for new netdevs.

   - Define Netlink protocol specification format which can be used to
     describe messages used by each family and auto-generate parsers.
     Add tools for generating kernel data structures and uAPI headers.

   - Expose all net/core sysctls inside netns.

   - Remove 4s sleep in netpoll if carrier is instantly detected on
     boot.

   - Add configurable limit of MDB entries per port, and port-vlan.

   - Continue populating drop reasons throughout the stack.

   - Retire a handful of legacy Qdiscs and classifiers.

  Protocols:

   - Support IPv4 big TCP (TSO frames larger than 64kB).

   - Add IP_LOCAL_PORT_RANGE socket option, to control local port range
     on socket by socket basis.

   - Track and report in procfs number of MPTCP sockets used.

   - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path
     manager.

   - IPv6: don't check net.ipv6.route.max_size and rely on garbage
     collection to free memory (similarly to IPv4).

   - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986).

   - ICMP: add per-rate limit counters.

   - Add support for user scanning requests in ieee802154.

   - Remove static WEP support.

   - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate
     reporting.

   - WiFi 7 EHT channel puncturing support (client & AP).

  BPF:

   - Add a rbtree data structure following the "next-gen data structure"
     precedent set by recently added linked list, that is, by using
     kfunc + kptr instead of adding a new BPF map type.

   - Expose XDP hints via kfuncs with initial support for RX hash and
     timestamp metadata.

   - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to
     better support decap on GRE tunnel devices not operating in collect
     metadata.

   - Improve x86 JIT's codegen for PROBE_MEM runtime error checks.

   - Remove the need for trace_printk_lock for bpf_trace_printk and
     bpf_trace_vprintk helpers.

   - Extend libbpf's bpf_tracing.h support for tracing arguments of
     kprobes/uprobes and syscall as a special case.

   - Significantly reduce the search time for module symbols by
     livepatch and BPF.

   - Enable cpumasks to be used as kptrs, which is useful for tracing
     programs tracking which tasks end up running on which CPUs in
     different time intervals.

   - Add support for BPF trampoline on s390x and riscv64.

   - Add capability to export the XDP features supported by the NIC.

   - Add __bpf_kfunc tag for marking kernel functions as kfuncs.

   - Add cgroup.memory=nobpf kernel parameter option to disable BPF
     memory accounting for container environments.

  Netfilter:

   - Remove the CLUSTERIP target. It has been marked as obsolete for
     years, and we still have WARN splats wrt races of the out-of-band
     /proc interface installed by this target.

   - Add 'destroy' commands to nf_tables. They are identical to the
     existing 'delete' commands, but do not return an error if the
     referenced object (set, chain, rule...) did not exist.

  Driver API:

   - Improve cpumask_local_spread() locality to help NICs set the right
     IRQ affinity on AMD platforms.

   - Separate C22 and C45 MDIO bus transactions more clearly.

   - Introduce new DCB table to control DSCP rewrite on egress.

   - Support configuration of Physical Layer Collision Avoidance (PLCA)
     Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of
     shared medium Ethernet.

   - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing
     preemption of low priority frames by high priority frames.

   - Add support for controlling MACSec offload using netlink SET.

   - Rework devlink instance refcounts to allow registration and
     de-registration under the instance lock. Split the code into
     multiple files, drop some of the unnecessarily granular locks and
     factor out common parts of netlink operation handling.

   - Add TX frame aggregation parameters (for USB drivers).

   - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning
     messages with notifications for debug.

   - Allow offloading of UDP NEW connections via act_ct.

   - Add support for per action HW stats in TC.

   - Support hardware miss to TC action (continue processing in SW from
     a specific point in the action chain).

   - Warn if old Wireless Extension user space interface is used with
     modern cfg80211/mac80211 drivers. Do not support Wireless
     Extensions for Wi-Fi 7 devices at all. Everyone should switch to
     using nl80211 interface instead.

   - Improve the CAN bit timing configuration. Use extack to return
     error messages directly to user space, update the SJW handling,
     including the definition of a new default value that will benefit
     CAN-FD controllers, by increasing their oscillator tolerance.

  New hardware / drivers:

   - Ethernet:
      - nVidia BlueField-3 support (control traffic driver)
      - Ethernet support for imx93 SoCs
      - Motorcomm yt8531 gigabit Ethernet PHY
      - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA)
      - Microchip LAN8841 PHY (incl. cable diagnostics and PTP)
      - Amlogic gxl MDIO mux

   - WiFi:
      - RealTek RTL8188EU (rtl8xxxu)
      - Qualcomm Wi-Fi 7 devices (ath12k)

   - CAN:
      - Renesas R-Car V4H

  Drivers:

   - Bluetooth:
      - Set Per Platform Antenna Gain (PPAG) for Intel controllers.

   - Ethernet NICs:
      - Intel (1G, igc):
         - support TSN / Qbv / packet scheduling features of i226 model
      - Intel (100G, ice):
         - use GNSS subsystem instead of TTY
         - multi-buffer XDP support
         - extend support for GPIO pins to E823 devices
      - nVidia/Mellanox:
         - update the shared buffer configuration on PFC commands
         - implement PTP adjphase function for HW offset control
         - TC support for Geneve and GRE with VF tunnel offload
         - more efficient crypto key management method
         - multi-port eswitch support
      - Netronome/Corigine:
         - add DCB IEEE support
         - support IPsec offloading for NFP3800
      - Freescale/NXP (enetc):
         - support XDP_REDIRECT for XDP non-linear buffers
         - improve reconfig, avoid link flap and waiting for idle
         - support MAC Merge layer
      - Other NICs:
         - sfc/ef100: add basic devlink support for ef100
         - ionic: rx_push mode operation (writing descriptors via MMIO)
         - bnxt: use the auxiliary bus abstraction for RDMA
         - r8169: disable ASPM and reset bus in case of tx timeout
         - cpsw: support QSGMII mode for J721e CPSW9G
         - cpts: support pulse-per-second output
         - ngbe: add an mdio bus driver
         - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing
         - r8152: handle devices with FW with NCM support
         - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation
         - virtio-net: support multi buffer XDP
         - virtio/vsock: replace virtio_vsock_pkt with sk_buff
         - tsnep: XDP support

   - Ethernet high-speed switches:
      - nVidia/Mellanox (mlxsw):
         - add support for latency TLV (in FW control messages)
      - Microchip (sparx5):
         - separate explicit and implicit traffic forwarding rules, make
           the implicit rules always active
         - add support for egress DSCP rewrite
         - IS0 VCAP support (Ingress Classification)
         - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS
           etc.)
         - ES2 VCAP support (Egress Access Control)
         - support for Per-Stream Filtering and Policing (802.1Q,
           8.6.5.1)

   - Ethernet embedded switches:
      - Marvell (mv88e6xxx):
         - add MAB (port auth) offload support
         - enable PTP receive for mv88e6390
      - NXP (ocelot):
         - support MAC Merge layer
         - support for the the vsc7512 internal copper phys
      - Microchip:
         - lan9303: convert to PHYLINK
         - lan966x: support TC flower filter statistics
         - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x
         - lan937x: support Credit Based Shaper configuration
         - ksz9477: support Energy Efficient Ethernet
      - other:
         - qca8k: convert to regmap read/write API, use bulk operations
         - rswitch: Improve TX timestamp accuracy

   - Intel WiFi (iwlwifi):
      - EHT (Wi-Fi 7) rate reporting
      - STEP equalizer support: transfer some STEP (connection to radio
        on platforms with integrated wifi) related parameters from the
        BIOS to the firmware.

   - Qualcomm 802.11ax WiFi (ath11k):
      - IPQ5018 support
      - Fine Timing Measurement (FTM) responder role support
      - channel 177 support

   - MediaTek WiFi (mt76):
      - per-PHY LED support
      - mt7996: EHT (Wi-Fi 7) support
      - Wireless Ethernet Dispatch (WED) reset support
      - switch to using page pool allocator

   - RealTek WiFi (rtw89):
      - support new version of Bluetooth co-existance

   - Mobile:
      - rmnet: support TX aggregation"

* tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits)
  page_pool: add a comment explaining the fragment counter usage
  net: ethtool: fix __ethtool_dev_mm_supported() implementation
  ethtool: pse-pd: Fix double word in comments
  xsk: add linux/vmalloc.h to xsk.c
  sefltests: netdevsim: wait for devlink instance after netns removal
  selftest: fib_tests: Always cleanup before exit
  net/mlx5e: Align IPsec ASO result memory to be as required by hardware
  net/mlx5e: TC, Set CT miss to the specific ct action instance
  net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG
  net/mlx5: Refactor tc miss handling to a single function
  net/mlx5: Kconfig: Make tc offload depend on tc skb extension
  net/sched: flower: Support hardware miss to tc action
  net/sched: flower: Move filter handle initialization earlier
  net/sched: cls_api: Support hardware miss to tc action
  net/sched: Rename user cookie and act cookie
  sfc: fix builds without CONFIG_RTC_LIB
  sfc: clean up some inconsistent indentings
  net/mlx4_en: Introduce flexible array to silence overflow warning
  net: lan966x: Fix possible deadlock inside PTP
  net/ulp: Remove redundant ->clone() test in inet_clone_ulp().
  ...

1 files changed, 992 insertions, 0 deletions

diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c
new file mode 100644
index 000000000..34488de55
--- /dev/null
+++ b/drivers/spi/spi-fsl-lpspi.c
@@ -0,0 +1,992 @@
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Freescale i.MX7ULP LPSPI driver
+//
+// Copyright 2016 Freescale Semiconductor, Inc.
+// Copyright 2018 NXP Semiconductors
+
+#include <linux/clk.h>
+#include <linux/completion.h>
+#include <linux/delay.h>
+#include <linux/dmaengine.h>
+#include <linux/dma-mapping.h>
+#include <linux/err.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/pinctrl/consumer.h>
+#include <linux/platform_device.h>
+#include <linux/dma/imx-dma.h>
+#include <linux/pm_runtime.h>
+#include <linux/slab.h>
+#include <linux/spi/spi.h>
+#include <linux/spi/spi_bitbang.h>
+#include <linux/types.h>
+
+#define DRIVER_NAME "fsl_lpspi"
+
+#define FSL_LPSPI_RPM_TIMEOUT 50 /* 50ms */
+
+/* The maximum bytes that edma can transfer once.*/
+#define FSL_LPSPI_MAX_EDMA_BYTES  ((1 << 15) - 1)
+
+/* i.MX7ULP LPSPI registers */
+#define IMX7ULP_VERID	0x0
+#define IMX7ULP_PARAM	0x4
+#define IMX7ULP_CR	0x10
+#define IMX7ULP_SR	0x14
+#define IMX7ULP_IER	0x18
+#define IMX7ULP_DER	0x1c
+#define IMX7ULP_CFGR0	0x20
+#define IMX7ULP_CFGR1	0x24
+#define IMX7ULP_DMR0	0x30
+#define IMX7ULP_DMR1	0x34
+#define IMX7ULP_CCR	0x40
+#define IMX7ULP_FCR	0x58
+#define IMX7ULP_FSR	0x5c
+#define IMX7ULP_TCR	0x60
+#define IMX7ULP_TDR	0x64
+#define IMX7ULP_RSR	0x70
+#define IMX7ULP_RDR	0x74
+
+/* General control register field define */
+#define CR_RRF		BIT(9)
+#define CR_RTF		BIT(8)
+#define CR_RST		BIT(1)
+#define CR_MEN		BIT(0)
+#define SR_MBF		BIT(24)
+#define SR_TCF		BIT(10)
+#define SR_FCF		BIT(9)
+#define SR_RDF		BIT(1)
+#define SR_TDF		BIT(0)
+#define IER_TCIE	BIT(10)
+#define IER_FCIE	BIT(9)
+#define IER_RDIE	BIT(1)
+#define IER_TDIE	BIT(0)
+#define DER_RDDE	BIT(1)
+#define DER_TDDE	BIT(0)
+#define CFGR1_PCSCFG	BIT(27)
+#define CFGR1_PINCFG	(BIT(24)|BIT(25))
+#define CFGR1_PCSPOL	BIT(8)
+#define CFGR1_NOSTALL	BIT(3)
+#define CFGR1_MASTER	BIT(0)
+#define FSR_TXCOUNT	(0xFF)
+#define RSR_RXEMPTY	BIT(1)
+#define TCR_CPOL	BIT(31)
+#define TCR_CPHA	BIT(30)
+#define TCR_CONT	BIT(21)
+#define TCR_CONTC	BIT(20)
+#define TCR_RXMSK	BIT(19)
+#define TCR_TXMSK	BIT(18)
+
+struct lpspi_config {
+	u8 bpw;
+	u8 chip_select;
+	u8 prescale;
+	u16 mode;
+	u32 speed_hz;
+};
+
+struct fsl_lpspi_data {
+	struct device *dev;
+	void __iomem *base;
+	unsigned long base_phys;
+	struct clk *clk_ipg;
+	struct clk *clk_per;
+	bool is_slave;
+	u32 num_cs;
+	bool is_only_cs1;
+	bool is_first_byte;
+
+	void *rx_buf;
+	const void *tx_buf;
+	void (*tx)(struct fsl_lpspi_data *);
+	void (*rx)(struct fsl_lpspi_data *);
+
+	u32 remain;
+	u8 watermark;
+	u8 txfifosize;
+	u8 rxfifosize;
+
+	struct lpspi_config config;
+	struct completion xfer_done;
+
+	bool slave_aborted;
+
+	/* DMA */
+	bool usedma;
+	struct completion dma_rx_completion;
+	struct completion dma_tx_completion;
+};
+
+static const struct of_device_id fsl_lpspi_dt_ids[] = {
+	{ .compatible = "fsl,imx7ulp-spi", },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, fsl_lpspi_dt_ids);
+
+#define LPSPI_BUF_RX(type)						\
+static void fsl_lpspi_buf_rx_##type(struct fsl_lpspi_data *fsl_lpspi)	\
+{									\
+	unsigned int val = readl(fsl_lpspi->base + IMX7ULP_RDR);	\
+									\
+	if (fsl_lpspi->rx_buf) {					\
+		*(type *)fsl_lpspi->rx_buf = val;			\
+		fsl_lpspi->rx_buf += sizeof(type);                      \
+	}								\
+}
+
+#define LPSPI_BUF_TX(type)						\
+static void fsl_lpspi_buf_tx_##type(struct fsl_lpspi_data *fsl_lpspi)	\
+{									\
+	type val = 0;							\
+									\
+	if (fsl_lpspi->tx_buf) {					\
+		val = *(type *)fsl_lpspi->tx_buf;			\
+		fsl_lpspi->tx_buf += sizeof(type);			\
+	}								\
+									\
+	fsl_lpspi->remain -= sizeof(type);				\
+	writel(val, fsl_lpspi->base + IMX7ULP_TDR);			\
+}
+
+LPSPI_BUF_RX(u8)
+LPSPI_BUF_TX(u8)
+LPSPI_BUF_RX(u16)
+LPSPI_BUF_TX(u16)
+LPSPI_BUF_RX(u32)
+LPSPI_BUF_TX(u32)
+
+static void fsl_lpspi_intctrl(struct fsl_lpspi_data *fsl_lpspi,
+			      unsigned int enable)
+{
+	writel(enable, fsl_lpspi->base + IMX7ULP_IER);
+}
+
+static int fsl_lpspi_bytes_per_word(const int bpw)
+{
+	return DIV_ROUND_UP(bpw, BITS_PER_BYTE);
+}
+
+static bool fsl_lpspi_can_dma(struct spi_controller *controller,
+			      struct spi_device *spi,
+			      struct spi_transfer *transfer)
+{
+	unsigned int bytes_per_word;
+
+	if (!controller->dma_rx)
+		return false;
+
+	bytes_per_word = fsl_lpspi_bytes_per_word(transfer->bits_per_word);
+
+	switch (bytes_per_word) {
+	case 1:
+	case 2:
+	case 4:
+		break;
+	default:
+		return false;
+	}
+
+	return true;
+}
+
+static int lpspi_prepare_xfer_hardware(struct spi_controller *controller)
+{
+	struct fsl_lpspi_data *fsl_lpspi =
+				spi_controller_get_devdata(controller);
+	int ret;
+
+	ret = pm_runtime_resume_and_get(fsl_lpspi->dev);
+	if (ret < 0) {
+		dev_err(fsl_lpspi->dev, "failed to enable clock\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static int lpspi_unprepare_xfer_hardware(struct spi_controller *controller)
+{
+	struct fsl_lpspi_data *fsl_lpspi =
+				spi_controller_get_devdata(controller);
+
+	pm_runtime_mark_last_busy(fsl_lpspi->dev);
+	pm_runtime_put_autosuspend(fsl_lpspi->dev);
+
+	return 0;
+}
+
+static void fsl_lpspi_write_tx_fifo(struct fsl_lpspi_data *fsl_lpspi)
+{
+	u8 txfifo_cnt;
+	u32 temp;
+
+	txfifo_cnt = readl(fsl_lpspi->base + IMX7ULP_FSR) & 0xff;
+
+	while (txfifo_cnt < fsl_lpspi->txfifosize) {
+		if (!fsl_lpspi->remain)
+			break;
+		fsl_lpspi->tx(fsl_lpspi);
+		txfifo_cnt++;
+	}
+
+	if (txfifo_cnt < fsl_lpspi->txfifosize) {
+		if (!fsl_lpspi->is_slave) {
+			temp = readl(fsl_lpspi->base + IMX7ULP_TCR);
+			temp &= ~TCR_CONTC;
+			writel(temp, fsl_lpspi->base + IMX7ULP_TCR);
+		}
+
+		fsl_lpspi_intctrl(fsl_lpspi, IER_FCIE);
+	} else
+		fsl_lpspi_intctrl(fsl_lpspi, IER_TDIE);
+}
+
+static void fsl_lpspi_read_rx_fifo(struct fsl_lpspi_data *fsl_lpspi)
+{
+	while (!(readl(fsl_lpspi->base + IMX7ULP_RSR) & RSR_RXEMPTY))
+		fsl_lpspi->rx(fsl_lpspi);
+}
+
+static void fsl_lpspi_set_cmd(struct fsl_lpspi_data *fsl_lpspi)
+{
+	u32 temp = 0;
+
+	temp |= fsl_lpspi->config.bpw - 1;
+	temp |= (fsl_lpspi->config.mode & 0x3) << 30;
+	temp |= (fsl_lpspi->config.chip_select & 0x3) << 24;
+	if (!fsl_lpspi->is_slave) {
+		temp |= fsl_lpspi->config.prescale << 27;
+		/*
+		 * Set TCR_CONT will keep SS asserted after current transfer.
+		 * For the first transfer, clear TCR_CONTC to assert SS.
+		 * For subsequent transfer, set TCR_CONTC to keep SS asserted.
+		 */
+		if (!fsl_lpspi->usedma) {
+			temp |= TCR_CONT;
+			if (fsl_lpspi->is_first_byte)
+				temp &= ~TCR_CONTC;
+			else
+				temp |= TCR_CONTC;
+		}
+	}
+	writel(temp, fsl_lpspi->base + IMX7ULP_TCR);
+
+	dev_dbg(fsl_lpspi->dev, "TCR=0x%x\n", temp);
+}
+
+static void fsl_lpspi_set_watermark(struct fsl_lpspi_data *fsl_lpspi)
+{
+	u32 temp;
+
+	if (!fsl_lpspi->usedma)
+		temp = fsl_lpspi->watermark >> 1 |
+		       (fsl_lpspi->watermark >> 1) << 16;
+	else
+		temp = fsl_lpspi->watermark >> 1;
+
+	writel(temp, fsl_lpspi->base + IMX7ULP_FCR);
+
+	dev_dbg(fsl_lpspi->dev, "FCR=0x%x\n", temp);
+}
+
+static int fsl_lpspi_set_bitrate(struct fsl_lpspi_data *fsl_lpspi)
+{
+	struct lpspi_config config = fsl_lpspi->config;
+	unsigned int perclk_rate, scldiv;
+	u8 prescale;
+
+	perclk_rate = clk_get_rate(fsl_lpspi->clk_per);
+
+	if (config.speed_hz > perclk_rate / 2) {
+		dev_err(fsl_lpspi->dev,
+		      "per-clk should be at least two times of transfer speed");
+		return -EINVAL;
+	}
+
+	for (prescale = 0; prescale < 8; prescale++) {
+		scldiv = perclk_rate / config.speed_hz / (1 << prescale) - 2;
+		if (scldiv < 256) {
+			fsl_lpspi->config.prescale = prescale;
+			break;
+		}
+	}
+
+	if (scldiv >= 256)
+		return -EINVAL;
+
+	writel(scldiv | (scldiv << 8) | ((scldiv >> 1) << 16),
+					fsl_lpspi->base + IMX7ULP_CCR);
+
+	dev_dbg(fsl_lpspi->dev, "perclk=%d, speed=%d, prescale=%d, scldiv=%d\n",
+		perclk_rate, config.speed_hz, prescale, scldiv);
+
+	return 0;
+}
+
+static int fsl_lpspi_dma_configure(struct spi_controller *controller)
+{
+	int ret;
+	enum dma_slave_buswidth buswidth;
+	struct dma_slave_config rx = {}, tx = {};
+	struct fsl_lpspi_data *fsl_lpspi =
+				spi_controller_get_devdata(controller);
+
+	switch (fsl_lpspi_bytes_per_word(fsl_lpspi->config.bpw)) {
+	case 4:
+		buswidth = DMA_SLAVE_BUSWIDTH_4_BYTES;
+		break;
+	case 2:
+		buswidth = DMA_SLAVE_BUSWIDTH_2_BYTES;
+		break;
+	case 1:
+		buswidth = DMA_SLAVE_BUSWIDTH_1_BYTE;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	tx.direction = DMA_MEM_TO_DEV;
+	tx.dst_addr = fsl_lpspi->base_phys + IMX7ULP_TDR;
+	tx.dst_addr_width = buswidth;
+	tx.dst_maxburst = 1;
+	ret = dmaengine_slave_config(controller->dma_tx, &tx);
+	if (ret) {
+		dev_err(fsl_lpspi->dev, "TX dma configuration failed with %d\n",
+			ret);
+		return ret;
+	}
+
+	rx.direction = DMA_DEV_TO_MEM;
+	rx.src_addr = fsl_lpspi->base_phys + IMX7ULP_RDR;
+	rx.src_addr_width = buswidth;
+	rx.src_maxburst = 1;
+	ret = dmaengine_slave_config(controller->dma_rx, &rx);
+	if (ret) {
+		dev_err(fsl_lpspi->dev, "RX dma configuration failed with %d\n",
+			ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int fsl_lpspi_config(struct fsl_lpspi_data *fsl_lpspi)
+{
+	u32 temp;
+	int ret;
+
+	if (!fsl_lpspi->is_slave) {
+		ret = fsl_lpspi_set_bitrate(fsl_lpspi);
+		if (ret)
+			return ret;
+	}
+
+	fsl_lpspi_set_watermark(fsl_lpspi);
+
+	if (!fsl_lpspi->is_slave)
+		temp = CFGR1_MASTER;
+	else
+		temp = CFGR1_PINCFG;
+	if (fsl_lpspi->config.mode & SPI_CS_HIGH)
+		temp |= CFGR1_PCSPOL;
+	writel(temp, fsl_lpspi->base + IMX7ULP_CFGR1);
+
+	temp = readl(fsl_lpspi->base + IMX7ULP_CR);
+	temp |= CR_RRF | CR_RTF | CR_MEN;
+	writel(temp, fsl_lpspi->base + IMX7ULP_CR);
+
+	temp = 0;
+	if (fsl_lpspi->usedma)
+		temp = DER_TDDE | DER_RDDE;
+	writel(temp, fsl_lpspi->base + IMX7ULP_DER);
+
+	return 0;
+}
+
+static int fsl_lpspi_setup_transfer(struct spi_controller *controller,
+				     struct spi_device *spi,
+				     struct spi_transfer *t)
+{
+	struct fsl_lpspi_data *fsl_lpspi =
+				spi_controller_get_devdata(spi->controller);
+
+	if (t == NULL)
+		return -EINVAL;
+
+	fsl_lpspi->config.mode = spi->mode;
+	fsl_lpspi->config.bpw = t->bits_per_word;
+	fsl_lpspi->config.speed_hz = t->speed_hz;
+	if (fsl_lpspi->is_only_cs1)
+		fsl_lpspi->config.chip_select = 1;
+	else
+		fsl_lpspi->config.chip_select = spi->chip_select;
+
+	if (!fsl_lpspi->config.speed_hz)
+		fsl_lpspi->config.speed_hz = spi->max_speed_hz;
+	if (!fsl_lpspi->config.bpw)
+		fsl_lpspi->config.bpw = spi->bits_per_word;
+
+	/* Initialize the functions for transfer */
+	if (fsl_lpspi->config.bpw <= 8) {
+		fsl_lpspi->rx = fsl_lpspi_buf_rx_u8;
+		fsl_lpspi->tx = fsl_lpspi_buf_tx_u8;
+	} else if (fsl_lpspi->config.bpw <= 16) {
+		fsl_lpspi->rx = fsl_lpspi_buf_rx_u16;
+		fsl_lpspi->tx = fsl_lpspi_buf_tx_u16;
+	} else {
+		fsl_lpspi->rx = fsl_lpspi_buf_rx_u32;
+		fsl_lpspi->tx = fsl_lpspi_buf_tx_u32;
+	}
+
+	if (t->len <= fsl_lpspi->txfifosize)
+		fsl_lpspi->watermark = t->len;
+	else
+		fsl_lpspi->watermark = fsl_lpspi->txfifosize;
+
+	if (fsl_lpspi_can_dma(controller, spi, t))
+		fsl_lpspi->usedma = true;
+	else
+		fsl_lpspi->usedma = false;
+
+	return fsl_lpspi_config(fsl_lpspi);
+}
+
+static int fsl_lpspi_slave_abort(struct spi_controller *controller)
+{
+	struct fsl_lpspi_data *fsl_lpspi =
+				spi_controller_get_devdata(controller);
+
+	fsl_lpspi->slave_aborted = true;
+	if (!fsl_lpspi->usedma)
+		complete(&fsl_lpspi->xfer_done);
+	else {
+		complete(&fsl_lpspi->dma_tx_completion);
+		complete(&fsl_lpspi->dma_rx_completion);
+	}
+
+	return 0;
+}
+
+static int fsl_lpspi_wait_for_completion(struct spi_controller *controller)
+{
+	struct fsl_lpspi_data *fsl_lpspi =
+				spi_controller_get_devdata(controller);
+
+	if (fsl_lpspi->is_slave) {
+		if (wait_for_completion_interruptible(&fsl_lpspi->xfer_done) ||
+			fsl_lpspi->slave_aborted) {
+			dev_dbg(fsl_lpspi->dev, "interrupted\n");
+			return -EINTR;
+		}
+	} else {
+		if (!wait_for_completion_timeout(&fsl_lpspi->xfer_done, HZ)) {
+			dev_dbg(fsl_lpspi->dev, "wait for completion timeout\n");
+			return -ETIMEDOUT;
+		}
+	}
+
+	return 0;
+}
+
+static int fsl_lpspi_reset(struct fsl_lpspi_data *fsl_lpspi)
+{
+	u32 temp;
+
+	if (!fsl_lpspi->usedma) {
+		/* Disable all interrupt */
+		fsl_lpspi_intctrl(fsl_lpspi, 0);
+	}
+
+	/* W1C for all flags in SR */
+	temp = 0x3F << 8;
+	writel(temp, fsl_lpspi->base + IMX7ULP_SR);
+
+	/* Clear FIFO and disable module */
+	temp = CR_RRF | CR_RTF;
+	writel(temp, fsl_lpspi->base + IMX7ULP_CR);
+
+	return 0;
+}
+
+static void fsl_lpspi_dma_rx_callback(void *cookie)
+{
+	struct fsl_lpspi_data *fsl_lpspi = (struct fsl_lpspi_data *)cookie;
+
+	complete(&fsl_lpspi->dma_rx_completion);
+}
+
+static void fsl_lpspi_dma_tx_callback(void *cookie)
+{
+	struct fsl_lpspi_data *fsl_lpspi = (struct fsl_lpspi_data *)cookie;
+
+	complete(&fsl_lpspi->dma_tx_completion);
+}
+
+static int fsl_lpspi_calculate_timeout(struct fsl_lpspi_data *fsl_lpspi,
+				       int size)
+{
+	unsigned long timeout = 0;
+
+	/* Time with actual data transfer and CS change delay related to HW */
+	timeout = (8 + 4) * size / fsl_lpspi->config.speed_hz;
+
+	/* Add extra second for scheduler related activities */
+	timeout += 1;
+
+	/* Double calculated timeout */
+	return msecs_to_jiffies(2 * timeout * MSEC_PER_SEC);
+}
+
+static int fsl_lpspi_dma_transfer(struct spi_controller *controller,
+				struct fsl_lpspi_data *fsl_lpspi,
+				struct spi_transfer *transfer)
+{
+	struct dma_async_tx_descriptor *desc_tx, *desc_rx;
+	unsigned long transfer_timeout;
+	unsigned long timeout;
+	struct sg_table *tx = &transfer->tx_sg, *rx = &transfer->rx_sg;
+	int ret;
+
+	ret = fsl_lpspi_dma_configure(controller);
+	if (ret)
+		return ret;
+
+	desc_rx = dmaengine_prep_slave_sg(controller->dma_rx,
+				rx->sgl, rx->nents, DMA_DEV_TO_MEM,
+				DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+	if (!desc_rx)
+		return -EINVAL;
+
+	desc_rx->callback = fsl_lpspi_dma_rx_callback;
+	desc_rx->callback_param = (void *)fsl_lpspi;
+	dmaengine_submit(desc_rx);
+	reinit_completion(&fsl_lpspi->dma_rx_completion);
+	dma_async_issue_pending(controller->dma_rx);
+
+	desc_tx = dmaengine_prep_slave_sg(controller->dma_tx,
+				tx->sgl, tx->nents, DMA_MEM_TO_DEV,
+				DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+	if (!desc_tx) {
+		dmaengine_terminate_all(controller->dma_tx);
+		return -EINVAL;
+	}
+
+	desc_tx->callback = fsl_lpspi_dma_tx_callback;
+	desc_tx->callback_param = (void *)fsl_lpspi;
+	dmaengine_submit(desc_tx);
+	reinit_completion(&fsl_lpspi->dma_tx_completion);
+	dma_async_issue_pending(controller->dma_tx);
+
+	fsl_lpspi->slave_aborted = false;
+
+	if (!fsl_lpspi->is_slave) {
+		transfer_timeout = fsl_lpspi_calculate_timeout(fsl_lpspi,
+							       transfer->len);
+
+		/* Wait eDMA to finish the data transfer.*/
+		timeout = wait_for_completion_timeout(&fsl_lpspi->dma_tx_completion,
+						      transfer_timeout);
+		if (!timeout) {
+			dev_err(fsl_lpspi->dev, "I/O Error in DMA TX\n");
+			dmaengine_terminate_all(controller->dma_tx);
+			dmaengine_terminate_all(controller->dma_rx);
+			fsl_lpspi_reset(fsl_lpspi);
+			return -ETIMEDOUT;
+		}
+
+		timeout = wait_for_completion_timeout(&fsl_lpspi->dma_rx_completion,
+						      transfer_timeout);
+		if (!timeout) {
+			dev_err(fsl_lpspi->dev, "I/O Error in DMA RX\n");
+			dmaengine_terminate_all(controller->dma_tx);
+			dmaengine_terminate_all(controller->dma_rx);
+			fsl_lpspi_reset(fsl_lpspi);
+			return -ETIMEDOUT;
+		}
+	} else {
+		if (wait_for_completion_interruptible(&fsl_lpspi->dma_tx_completion) ||
+			fsl_lpspi->slave_aborted) {
+			dev_dbg(fsl_lpspi->dev,
+				"I/O Error in DMA TX interrupted\n");
+			dmaengine_terminate_all(controller->dma_tx);
+			dmaengine_terminate_all(controller->dma_rx);
+			fsl_lpspi_reset(fsl_lpspi);
+			return -EINTR;
+		}
+
+		if (wait_for_completion_interruptible(&fsl_lpspi->dma_rx_completion) ||
+			fsl_lpspi->slave_aborted) {
+			dev_dbg(fsl_lpspi->dev,
+				"I/O Error in DMA RX interrupted\n");
+			dmaengine_terminate_all(controller->dma_tx);
+			dmaengine_terminate_all(controller->dma_rx);
+			fsl_lpspi_reset(fsl_lpspi);
+			return -EINTR;
+		}
+	}
+
+	fsl_lpspi_reset(fsl_lpspi);
+
+	return 0;
+}
+
+static void fsl_lpspi_dma_exit(struct spi_controller *controller)
+{
+	if (controller->dma_rx) {
+		dma_release_channel(controller->dma_rx);
+		controller->dma_rx = NULL;
+	}
+
+	if (controller->dma_tx) {
+		dma_release_channel(controller->dma_tx);
+		controller->dma_tx = NULL;
+	}
+}
+
+static int fsl_lpspi_dma_init(struct device *dev,
+			      struct fsl_lpspi_data *fsl_lpspi,
+			      struct spi_controller *controller)
+{
+	int ret;
+
+	/* Prepare for TX DMA: */
+	controller->dma_tx = dma_request_chan(dev, "tx");
+	if (IS_ERR(controller->dma_tx)) {
+		ret = PTR_ERR(controller->dma_tx);
+		dev_dbg(dev, "can't get the TX DMA channel, error %d!\n", ret);
+		controller->dma_tx = NULL;
+		goto err;
+	}
+
+	/* Prepare for RX DMA: */
+	controller->dma_rx = dma_request_chan(dev, "rx");
+	if (IS_ERR(controller->dma_rx)) {
+		ret = PTR_ERR(controller->dma_rx);
+		dev_dbg(dev, "can't get the RX DMA channel, error %d\n", ret);
+		controller->dma_rx = NULL;
+		goto err;
+	}
+
+	init_completion(&fsl_lpspi->dma_rx_completion);
+	init_completion(&fsl_lpspi->dma_tx_completion);
+	controller->can_dma = fsl_lpspi_can_dma;
+	controller->max_dma_len = FSL_LPSPI_MAX_EDMA_BYTES;
+
+	return 0;
+err:
+	fsl_lpspi_dma_exit(controller);
+	return ret;
+}
+
+static int fsl_lpspi_pio_transfer(struct spi_controller *controller,
+				  struct spi_transfer *t)
+{
+	struct fsl_lpspi_data *fsl_lpspi =
+				spi_controller_get_devdata(controller);
+	int ret;
+
+	fsl_lpspi->tx_buf = t->tx_buf;
+	fsl_lpspi->rx_buf = t->rx_buf;
+	fsl_lpspi->remain = t->len;
+
+	reinit_completion(&fsl_lpspi->xfer_done);
+	fsl_lpspi->slave_aborted = false;
+
+	fsl_lpspi_write_tx_fifo(fsl_lpspi);
+
+	ret = fsl_lpspi_wait_for_completion(controller);
+	if (ret)
+		return ret;
+
+	fsl_lpspi_reset(fsl_lpspi);
+
+	return 0;
+}
+
+static int fsl_lpspi_transfer_one(struct spi_controller *controller,
+				  struct spi_device *spi,
+				  struct spi_transfer *t)
+{
+	struct fsl_lpspi_data *fsl_lpspi =
+					spi_controller_get_devdata(controller);
+	int ret;
+
+	fsl_lpspi->is_first_byte = true;
+	ret = fsl_lpspi_setup_transfer(controller, spi, t);
+	if (ret < 0)
+		return ret;
+
+	fsl_lpspi_set_cmd(fsl_lpspi);
+	fsl_lpspi->is_first_byte = false;
+
+	if (fsl_lpspi->usedma)
+		ret = fsl_lpspi_dma_transfer(controller, fsl_lpspi, t);
+	else
+		ret = fsl_lpspi_pio_transfer(controller, t);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static irqreturn_t fsl_lpspi_isr(int irq, void *dev_id)
+{
+	u32 temp_SR, temp_IER;
+	struct fsl_lpspi_data *fsl_lpspi = dev_id;
+
+	temp_IER = readl(fsl_lpspi->base + IMX7ULP_IER);
+	fsl_lpspi_intctrl(fsl_lpspi, 0);
+	temp_SR = readl(fsl_lpspi->base + IMX7ULP_SR);
+
+	fsl_lpspi_read_rx_fifo(fsl_lpspi);
+
+	if ((temp_SR & SR_TDF) && (temp_IER & IER_TDIE)) {
+		fsl_lpspi_write_tx_fifo(fsl_lpspi);
+		return IRQ_HANDLED;
+	}
+
+	if (temp_SR & SR_MBF ||
+	    readl(fsl_lpspi->base + IMX7ULP_FSR) & FSR_TXCOUNT) {
+		writel(SR_FCF, fsl_lpspi->base + IMX7ULP_SR);
+		fsl_lpspi_intctrl(fsl_lpspi, IER_FCIE);
+		return IRQ_HANDLED;
+	}
+
+	if (temp_SR & SR_FCF && (temp_IER & IER_FCIE)) {
+		writel(SR_FCF, fsl_lpspi->base + IMX7ULP_SR);
+		complete(&fsl_lpspi->xfer_done);
+		return IRQ_HANDLED;
+	}
+
+	return IRQ_NONE;
+}
+
+#ifdef CONFIG_PM
+static int fsl_lpspi_runtime_resume(struct device *dev)
+{
+	struct spi_controller *controller = dev_get_drvdata(dev);
+	struct fsl_lpspi_data *fsl_lpspi;
+	int ret;
+
+	fsl_lpspi = spi_controller_get_devdata(controller);
+
+	ret = clk_prepare_enable(fsl_lpspi->clk_per);
+	if (ret)
+		return ret;
+
+	ret = clk_prepare_enable(fsl_lpspi->clk_ipg);
+	if (ret) {
+		clk_disable_unprepare(fsl_lpspi->clk_per);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int fsl_lpspi_runtime_suspend(struct device *dev)
+{
+	struct spi_controller *controller = dev_get_drvdata(dev);
+	struct fsl_lpspi_data *fsl_lpspi;
+
+	fsl_lpspi = spi_controller_get_devdata(controller);
+
+	clk_disable_unprepare(fsl_lpspi->clk_per);
+	clk_disable_unprepare(fsl_lpspi->clk_ipg);
+
+	return 0;
+}
+#endif
+
+static int fsl_lpspi_init_rpm(struct fsl_lpspi_data *fsl_lpspi)
+{
+	struct device *dev = fsl_lpspi->dev;
+
+	pm_runtime_enable(dev);
+	pm_runtime_set_autosuspend_delay(dev, FSL_LPSPI_RPM_TIMEOUT);
+	pm_runtime_use_autosuspend(dev);
+
+	return 0;
+}
+
+static int fsl_lpspi_probe(struct platform_device *pdev)
+{
+	struct fsl_lpspi_data *fsl_lpspi;
+	struct spi_controller *controller;
+	struct resource *res;
+	int ret, irq;
+	u32 temp;
+	bool is_slave;
+
+	is_slave = of_property_read_bool((&pdev->dev)->of_node, "spi-slave");
+	if (is_slave)
+		controller = spi_alloc_slave(&pdev->dev,
+					sizeof(struct fsl_lpspi_data));
+	else
+		controller = spi_alloc_master(&pdev->dev,
+					sizeof(struct fsl_lpspi_data));
+
+	if (!controller)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, controller);
+
+	fsl_lpspi = spi_controller_get_devdata(controller);
+	fsl_lpspi->dev = &pdev->dev;
+	fsl_lpspi->is_slave = is_slave;
+	fsl_lpspi->is_only_cs1 = of_property_read_bool((&pdev->dev)->of_node,
+						"fsl,spi-only-use-cs1-sel");
+	if (of_property_read_u32((&pdev->dev)->of_node, "num-cs",
+				 &fsl_lpspi->num_cs))
+		fsl_lpspi->num_cs = 1;
+
+	controller->bits_per_word_mask = SPI_BPW_RANGE_MASK(8, 32);
+	controller->transfer_one = fsl_lpspi_transfer_one;
+	controller->prepare_transfer_hardware = lpspi_prepare_xfer_hardware;
+	controller->unprepare_transfer_hardware = lpspi_unprepare_xfer_hardware;
+	controller->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH;
+	controller->flags = SPI_MASTER_MUST_RX | SPI_MASTER_MUST_TX;
+	controller->dev.of_node = pdev->dev.of_node;
+	controller->bus_num = pdev->id;
+	controller->num_chipselect = fsl_lpspi->num_cs;
+	controller->slave_abort = fsl_lpspi_slave_abort;
+	if (!fsl_lpspi->is_slave)
+		controller->use_gpio_descriptors = true;
+
+	init_completion(&fsl_lpspi->xfer_done);
+
+	fsl_lpspi->base = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
+	if (IS_ERR(fsl_lpspi->base)) {
+		ret = PTR_ERR(fsl_lpspi->base);
+		goto out_controller_put;
+	}
+	fsl_lpspi->base_phys = res->start;
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
+		ret = irq;
+		goto out_controller_put;
+	}
+
+	ret = devm_request_irq(&pdev->dev, irq, fsl_lpspi_isr, 0,
+			       dev_name(&pdev->dev), fsl_lpspi);
+	if (ret) {
+		dev_err(&pdev->dev, "can't get irq%d: %d\n", irq, ret);
+		goto out_controller_put;
+	}
+
+	fsl_lpspi->clk_per = devm_clk_get(&pdev->dev, "per");
+	if (IS_ERR(fsl_lpspi->clk_per)) {
+		ret = PTR_ERR(fsl_lpspi->clk_per);
+		goto out_controller_put;
+	}
+
+	fsl_lpspi->clk_ipg = devm_clk_get(&pdev->dev, "ipg");
+	if (IS_ERR(fsl_lpspi->clk_ipg)) {
+		ret = PTR_ERR(fsl_lpspi->clk_ipg);
+		goto out_controller_put;
+	}
+
+	/* enable the clock */
+	ret = fsl_lpspi_init_rpm(fsl_lpspi);
+	if (ret)
+		goto out_controller_put;
+
+	ret = pm_runtime_get_sync(fsl_lpspi->dev);
+	if (ret < 0) {
+		dev_err(fsl_lpspi->dev, "failed to enable clock\n");
+		goto out_pm_get;
+	}
+
+	temp = readl(fsl_lpspi->base + IMX7ULP_PARAM);
+	fsl_lpspi->txfifosize = 1 << (temp & 0x0f);
+	fsl_lpspi->rxfifosize = 1 << ((temp >> 8) & 0x0f);
+
+	ret = fsl_lpspi_dma_init(&pdev->dev, fsl_lpspi, controller);
+	if (ret == -EPROBE_DEFER)
+		goto out_pm_get;
+
+	if (ret < 0)
+		dev_err(&pdev->dev, "dma setup error %d, use pio\n", ret);
+
+	ret = devm_spi_register_controller(&pdev->dev, controller);
+	if (ret < 0) {
+		dev_err_probe(&pdev->dev, ret, "spi_register_controller error\n");
+		goto free_dma;
+	}
+
+	pm_runtime_mark_last_busy(fsl_lpspi->dev);
+	pm_runtime_put_autosuspend(fsl_lpspi->dev);
+
+	return 0;
+
+free_dma:
+	fsl_lpspi_dma_exit(controller);
+out_pm_get:
+	pm_runtime_dont_use_autosuspend(fsl_lpspi->dev);
+	pm_runtime_put_sync(fsl_lpspi->dev);
+	pm_runtime_disable(fsl_lpspi->dev);
+out_controller_put:
+	spi_controller_put(controller);
+
+	return ret;
+}
+
+static int fsl_lpspi_remove(struct platform_device *pdev)
+{
+	struct spi_controller *controller = platform_get_drvdata(pdev);
+	struct fsl_lpspi_data *fsl_lpspi =
+				spi_controller_get_devdata(controller);
+
+	fsl_lpspi_dma_exit(controller);
+
+	pm_runtime_disable(fsl_lpspi->dev);
+	return 0;
+}
+
+static int __maybe_unused fsl_lpspi_suspend(struct device *dev)
+{
+	pinctrl_pm_select_sleep_state(dev);
+	return pm_runtime_force_suspend(dev);
+}
+
+static int __maybe_unused fsl_lpspi_resume(struct device *dev)
+{
+	int ret;
+
+	ret = pm_runtime_force_resume(dev);
+	if (ret) {
+		dev_err(dev, "Error in resume: %d\n", ret);
+		return ret;
+	}
+
+	pinctrl_pm_select_default_state(dev);
+
+	return 0;
+}
+
+static const struct dev_pm_ops fsl_lpspi_pm_ops = {
+	SET_RUNTIME_PM_OPS(fsl_lpspi_runtime_suspend,
+				fsl_lpspi_runtime_resume, NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(fsl_lpspi_suspend, fsl_lpspi_resume)
+};
+
+static struct platform_driver fsl_lpspi_driver = {
+	.driver = {
+		.name = DRIVER_NAME,
+		.of_match_table = fsl_lpspi_dt_ids,
+		.pm = &fsl_lpspi_pm_ops,
+	},
+	.probe = fsl_lpspi_probe,
+	.remove = fsl_lpspi_remove,
+};
+module_platform_driver(fsl_lpspi_driver);
+
+MODULE_DESCRIPTION("LPSPI Controller driver");
+MODULE_AUTHOR("Gao Pan <pandy.gao@nxp.com>");
+MODULE_LICENSE("GPL");